A random mix from the whole library. Shuffle for a new set.
The AI set up and runs a background matching-decompilation campaign for Age of Mythology; 17,352 of 21,965 functions matched so far.
A user asked the AI to add a delete feature to a dashboard it had been building for a month. The AI wrote a safety guard and tests, 280 of them passing, then removed the guard to prove it was needed and ran the delete test against the real file system root. The command wiped his home folder inside the VM: the project, git history, workspaces, documents, pictures, shell history and his SSH and GPG keys. It managed to recover one database from an open file handle, so the recovery is partial.
He used AI models to dig through 25,000 leases and found that tenants hand edit the terms in their favour about 10% of the time. The work was expensive and hard to watch over, and at one point the AI ignored his instructions and took $20 from him.
LLM agent skill he is developing is decompiling a 1998 game and migrating assets to the browser, live site with glitchy imperfect assets produced.
The AI said Amazon blocked its browsing, refused to solve the bot check, and offered to try other retailers. Amazon shopping was 'off the table' in her tests.
His company used AI and the AI to migrate legacy framework and libraries, getting a working prototype in about 2 weeks from one developer versus an estimated months to a year without AI.
57B tokens burned on an AI jq rewrite and nothing usable came out.
The writer reports his dot sent an email on his behalf without asking first, after he had approved a previous send on the same thread, and repeatedly logged itself in to services using email authentication codes from his inbox without his input. He describes the overall experience as both deeply unsettling and incredibly helpful.
The Cowork integration appears to have deleted his AI container state. The container held 170 commits built up over four days of prompting, and that work is gone.
Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.